ucimlr.regression_datasets

all_datasets

all_datasets()

Returns a list of all RegressionDataset classes.

Abalone

class Abalone(RegressionDataset):
 |  Abalone(root, split=TRAIN, validation_size=0.2)

Link to the dataset description.

Parameters

  • root (str): Local path for storing/reading dataset files.
  • split (str): One of {'train', 'validation', 'test'}
  • validation_size (float): How large fraction in (0, 1) of the training partition to use for validation.

AirFoil

class AirFoil(RegressionDataset):
 |  AirFoil(root, split=TRAIN, validation_size=0.2)

Link to the dataset description.

Parameters

  • root (str): Local path for storing/reading dataset files.
  • split (str): One of {'train', 'validation', 'test'}
  • validation_size (float): How large fraction in (0, 1) of the training partition to use for validation.

AirQuality

class AirQuality(RegressionDataset):
 |  AirQuality(root, split=TRAIN, validation_size=0.2)

Parameters

  • root (str): Local path for storing/reading dataset files.
  • split (str): One of {'train', 'validation', 'test'}
  • validation_size (float): How large fraction in (0, 1) of the training partition to use for validation.

BlogFeedback

class BlogFeedback(RegressionDataset):
 |  BlogFeedback(root, split=TRAIN, validation_size=0.2)

Link to the dataset description.

Parameters

  • root (str): Local path for storing/reading dataset files.
  • split (str): One of {'train', 'validation', 'test'}
  • validation_size (float): How large fraction in (0, 1) of the training partition to use for validation.

CTSlices

class CTSlices(RegressionDataset):
 |  CTSlices(root, split=TRAIN, validation_size=0.2)

Parameters

  • root (str): Local path for storing/reading dataset files.
  • split (str): One of {'train', 'validation', 'test'}
  • validation_size (float): How large fraction in (0, 1) of the training partition to use for validation.

FacebookComments

class FacebookComments(RegressionDataset):
 |  FacebookComments(root, split=TRAIN, validation_size=0.2)

Predict the number of likes on posts from a collection of Facebook pages. Every page has multiple posts, making the number of pages less than the samples in the dataset (each sample is one post).

Note

The provided test split has a relatively large discrepancy in terms of distributions of the features and targets. Training and validation splits are also made to ensure that the same page is not in both splits. This makes the distributions of features in training and validation splits vary to a relatively large extent, possible because the number of pages are not that many, while the features are many.

Link to the dataset description.

Parameters

  • root (str): Local path for storing/reading dataset files.
  • split (str): One of {'train', 'validation', 'test'}
  • validation_size (float): How large fraction in (0, 1) of the training partition to use for validation.

OnlineNews

class OnlineNews(RegressionDataset):
 |  OnlineNews(root, split=TRAIN, validation_size=0.2)

Parameters

  • root (str): Local path for storing/reading dataset files.
  • split (str): One of {'train', 'validation', 'test'}
  • validation_size (float): How large fraction in (0, 1) of the training partition to use for validation.

Parkinson

class Parkinson(RegressionDataset):
 |  Parkinson(root, split=TRAIN, validation_size=0.2)

Link to the dataset description.

Parameters

  • root (str): Local path for storing/reading dataset files.
  • split (str): One of {'train', 'validation', 'test'}
  • validation_size (float): How large fraction in (0, 1) of the training partition to use for validation.

PowerPlant

class PowerPlant(RegressionDataset):
 |  PowerPlant(root, split=TRAIN, validation_size=0.2)

Parameters

  • root (str): Local path for storing/reading dataset files.
  • split (str): One of {'train', 'validation', 'test'}
  • validation_size (float): How large fraction in (0, 1) of the training partition to use for validation.

RealEstate

class RealEstate(RegressionDataset):
 |  RealEstate(root, split=TRAIN, validation_size=0.2)

Link to the dataset description.

Parameters

  • root (str): Local path for storing/reading dataset files.
  • split (str): One of {'train', 'validation', 'test'}
  • validation_size (float): How large fraction in (0, 1) of the training partition to use for validation.

Superconductivity

class Superconductivity(RegressionDataset):
 |  Superconductivity(root, split=TRAIN, validation_size=0.2)

Parameters

  • root (str): Local path for storing/reading dataset files.
  • split (str): One of {'train', 'validation', 'test'}
  • validation_size (float): How large fraction in (0, 1) of the training partition to use for validation.

WhiteWineQuality

class WhiteWineQuality(RegressionDataset):
 |  WhiteWineQuality(root, split=TRAIN, validation_size=0.2)

Description of dataset here.

Citation:

P. Cortez, A. Cerdeira, F. Almeida, T. Matos and J. Reis.
Modeling wine preferences by data mining from physicochemical properties.
In Decision Support Systems, Elsevier, 47(4):547-553, 2009.

Parameters

  • root (str): Local path for storing/reading dataset files.
  • split (str): One of {'train', 'validation', 'test'}
  • validation_size (float): How large fraction in (0, 1) of the training partition to use for validation.